Problem
Research questions and friction points this paper is trying to address.
3D shape optimization
generative priors
sketch-conditioned design
distribution drift
AnchorGen: Anchored Optimization for Customizable Generative 3D Design
🤖 AI Summary
This study addresses the issue in generative 3D optimization where prior distributions overlook sketch styles, leading to design deviations. We propose a condition-free training method based on a rectified flow framework. Exploiting the submanifold properties of the joint distribution, shape latents are optimized via gradient descent during inference, while a token-level cosine penalty is introduced to constrain sketch latents. Furthermore, differentiable drag proxies are incorporated to achieve anchored control. The proposed approach supports design-preserving optimization, explicit dimensional editing, and pure sketch-based synthesis. By ensuring geometric validity while maintaining design fidelity, this work significantly enhances the controllability of customized 3D generation.
📝 Abstract
Engineering design often starts from a 2D sketch that fixes style and proportions, yet the subsequent 3D shape optimization relies on learned generative priors to keep the geometry valid. However, these priors are agnostic to the sketch: while they admit a valid design by correcting a drifted proposal back to its training distribution, they often correct it towards the high-density region, ignoring the specified design. We introduce \emph{AnchorGen}, a rectified-flow framework trained unconditionally on the concatenated shape and sketch latents of paired data. The learned manifold represents the joint distribution of shape-sketch pairs, so constraining the sketch component restricts the iterate to the sub-manifold of shapes consistent with a target style. Since training employs no conditioning signal, the constraint is imposed at inference: gradient descent optimizes the shape latent to minimize a differentiable drag surrogate, while constraining the sketch latent to remain close to the target sketch via a token-wise cosine penalty. A single model thereby supports design-preserving optimization, dimensionally explicit design edits, and sketch-only synthesis.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Rectified Flow
Joint Latent Manifold
Inference-time Constraint
Sketch-conditioned 3D Generation
Differentiable Drag Surrogate
🔎 Similar Papers
No similar papers found.
